Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to political unity

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to unity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ================================================================
    -0.77
    nov
    -0.76
    apons
    -0.76
    200000
    -0.71
    entious
    -0.68
    hyde
    -0.68
    resp
    -0.68
    phrine
    -0.67
    random
    -0.67
    lem
    -0.66
    POSITIVE LOGITS
     unity
    0.90
    halla
    0.81
    arity
    0.81
     cohesion
    0.80
     harmony
    0.79
    iversal
    0.79
     sworn
    0.77
     assurance
    0.74
    eous
    0.71
    yip
    0.71
    Act Density 0.015%

    No Known Activations